US11896455B2 - Method and system for braces removal from dentition mesh - Google Patents
Method and system for braces removal from dentition mesh Download PDFInfo
- Publication number
- US11896455B2 US11896455B2 US17/555,797 US202117555797A US11896455B2 US 11896455 B2 US11896455 B2 US 11896455B2 US 202117555797 A US202117555797 A US 202117555797A US 11896455 B2 US11896455 B2 US 11896455B2
- Authority
- US
- United States
- Prior art keywords
- mesh
- bracket
- digital mesh
- digital
- dentition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
- 238000000034 method Methods 0.000 title claims abstract description 122
- 230000036346 tooth eruption Effects 0.000 title claims abstract description 101
- 210000004513 dentition Anatomy 0.000 title claims abstract description 100
- 238000012545 processing Methods 0.000 claims abstract description 73
- 210000001519 tissue Anatomy 0.000 claims abstract description 18
- 210000002455 dental arch Anatomy 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims description 129
- 238000001514 detection method Methods 0.000 claims description 40
- 238000003384 imaging method Methods 0.000 claims description 38
- 238000004422 calculation algorithm Methods 0.000 claims description 36
- 230000008569 process Effects 0.000 claims description 27
- 230000002452 interceptive effect Effects 0.000 claims description 11
- 238000007670 refining Methods 0.000 claims description 10
- 230000000877 morphologic effect Effects 0.000 claims description 5
- 230000010339 dilation Effects 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 210000004210 tooth component Anatomy 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 37
- 238000013138 pruning Methods 0.000 description 12
- 238000013459 approach Methods 0.000 description 11
- 238000007408 cone-beam computed tomography Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 10
- 238000005286 illumination Methods 0.000 description 10
- 230000003287 optical effect Effects 0.000 description 9
- 239000013598 vector Substances 0.000 description 9
- 241000270295 Serpentes Species 0.000 description 8
- 230000008901 benefit Effects 0.000 description 8
- 238000003860 storage Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 5
- 210000001847 jaw Anatomy 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 239000003973 paint Substances 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000010990 cephalometric method Methods 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000003825 pressing Methods 0.000 description 4
- 238000012552 review Methods 0.000 description 4
- 238000012800 visualization Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 210000003298 dental enamel Anatomy 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000000926 separation method Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 239000000872 buffer Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 239000012536 storage buffer Substances 0.000 description 2
- 210000000332 tooth crown Anatomy 0.000 description 2
- 238000011179 visual inspection Methods 0.000 description 2
- 206010073306 Exposure to radiation Diseases 0.000 description 1
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 206010061274 Malocclusion Diseases 0.000 description 1
- 208000034718 Tooth crowding Diseases 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000011960 computer-aided design Methods 0.000 description 1
- 238000004195 computer-aided diagnosis Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000000763 evoking effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003711 image thresholding Methods 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000005865 ionizing radiation Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000007406 plaque accumulation Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010186 staining Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
- A61C7/00—Orthodontics, i.e. obtaining or maintaining the desired position of teeth, e.g. by straightening, evening, regulating, separating, or by correcting malocclusions
- A61C7/002—Orthodontic computer assisted systems
-
- A61B6/51—
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5252—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data removing objects from field of view, e.g. removing patient table from a CT image
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
- A61C7/00—Orthodontics, i.e. obtaining or maintaining the desired position of teeth, e.g. by straightening, evening, regulating, separating, or by correcting malocclusions
- A61C7/02—Tools for manipulating or working with an orthodontic appliance
- A61C7/023—Tools for manipulating or working with an orthodontic appliance for debonding or removing orthodontic devices
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
- A61C7/00—Orthodontics, i.e. obtaining or maintaining the desired position of teeth, e.g. by straightening, evening, regulating, separating, or by correcting malocclusions
- A61C7/12—Brackets; Arch wires; Combinations thereof; Accessories therefor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61C—DENTISTRY; APPARATUS OR METHODS FOR ORAL OR DENTAL HYGIENE
- A61C9/00—Impression cups, i.e. impression trays; Impression methods
- A61C9/004—Means or methods for taking digitized impressions
- A61C9/0046—Data acquisition means or methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
- G06T2219/20—Indexing scheme for editing of 3D models
Definitions
- the disclosure relates generally to manipulation of elements that are represented by a three-dimensional mesh and more particularly to methods and apparatus for tooth crown surface characterization in a surface contour image that has been obtained using reflectance imaging.
- 3-D imaging and 3-D image processing are of growing interest to dental/orthodontic practitioners for computer-aided diagnosis, for prosthesis design and fabrication, and for overall improved patient care.
- 3-D imaging and 3-D image processing offer significant advantages in terms of flexibility, accuracy, and repeatability.
- 3-D cephalometric analysis overcomes some of the shortcomings associated with conventional methods of two-dimensional (2-D) cephalometric analysis, such as 2-D geometric errors of perspective projection, magnification, and head positioning in projection, for example.
- 3-D cephalometrics has been shown to yield objective data that is more accurate, since it is based on calculation rather than being largely dependent upon discrete measurements, as is the case with 2-D cephalometrics.
- Optical intraoral scans in general, produce contours of dentition objects and have been helpful in improving visualization of teeth, gums, and other intra-oral structures.
- Surface contour characterization using visible or near-visible light can be particularly useful for assessment of tooth condition and has recognized value for various types of dental procedures, such as for restorative dentistry. This can provide a valuable tool to assist the dental practitioner in identifying various problems and in validating other measurements and observations related to the patient's teeth and supporting structures.
- Surface contour information can also be used to generate 3-D models of dentition components such as individual teeth; the position and orientation information related to individual teeth can then be used in assessing orthodontic treatment progress. With proper use of surface contour imaging, the need: for multiple 2-D or 3-D X-ray acquisitions of a patient's dentition can be avoided.
- Optical 3-dimensional (3-D) measurement methods provide shape and spatial information using light directed onto a surface in various ways.
- types of imaging methods used for contour imaging are fringe or structured light projection devices.
- Structured light projection imaging uses patterned or structured light and camera/sensor triangulation to obtain surface contour information for structures of various types.
- a point cloud can be generated.
- a mesh can then be formed from the point cloud or a plurality of point clouds, in order to reconstruct at least a planar approximation to the surface.
- Mesh representation can be particularly useful for showing surface structure of teeth and gums and can be obtained using a handheld camera and without requiring harmful radiation levels.
- mesh representation has been found to lack some of the inherent versatility and utility that is available using cone-beam computed tomography (CBCT) or other techniques that expose the patient to radiation.
- CBCT cone-beam computed tomography
- One area in which mesh representation has yielded only disappointing results relates to segmentation. Segmentation allows the practitioner to identify and isolate the crown and other visible portions of the tooth from gums and related supporting structure. Conventional methods for segmentation of mesh images can often be inaccurate and may fail to distinguish tooth structure from supporting tissues.
- U.S. Pat. No. 8,738,165 to Cinader Jr. et al. entitled “Methods of preparing a virtual dentition model and fabricating a dental retainer therefrom”, discloses a virtual model of a dental patient's dentition provided by obtaining a digital data file of the patient's teeth and orthodontic appliances connected to the teeth, and combined with data from the data file with other data that represents surfaces of the teeth underlying the appliances.
- the virtual model is used in preparing a physical model of the patient's current dentition that can be used to make a dental retainer.
- the '165 disclosure also notes editing tools used in image manipulating software to remove the data representing the orthodontic appliances.
- Image manipulating software described in the '165 disclosure is “Geomagic Studio” (from Geomagic, Inc. of Research Triangle Park, N.C.), in which portions of an image are identified and deleted by a technician using a computer mouse or other input device.
- the U.S. Pat. No. 8,738,165 disclosure further mentions software known as “ZBrush” (from Pixologic, Inc. of Los Angeles, Calif.) used to digitally/manually fine-tune and sculpt the combined data. These methods can require considerable operator skill and results can be highly subjective.
- An aspect of this application is to advance the art, of tooth segmentation and/or manipulation in relation to volume imaging and visualization used in medical and dental applications.
- Another aspect of this application is to address, in whole or in part, at least the foregoing and other deficiencies in the related art. It is another aspect of this application to provide, in whole or in part, at least the advantages described herein.
- Certain exemplary method and/or apparatus embodiments according to the present disclosure can address particular needs for improved visualization and assessment of 3D dentition models, where brace representations have been removed or reduced and tooth surfaces added or restored for clarity.
- Restored 3D dentition models can be used with internal structures obtained using CBCT and other radiographic volume imaging methods or can be correlated to reflectance image data obtained from the patient.
- a method for generating a digital model of reconstructed dentition can include obtaining a 3-D digital mesh model of the patient's dentition including braces, teeth, and gingival, modifying the 3-D digital mesh dentition model by removing wire portions of the braces therefrom, modifying the 3-D digital mesh dentition model by removing bracket portions of the braces therefrom, approximating teeth surfaces of the modified 3-D digital mesh dentition model previously covered by the wire portions and the bracket portions of the braces, and displaying, storing, or transmitting over a network to another computer, the reconstructed 3-D digital mesh dentition model.
- a method for generating a digital model of a patient's dentition executed at least in part by a computer that can include acquiring a 3-D digital mesh that is representative of the patient's dentition along a dental arch, wherein the digital mesh includes braces, teeth, and gingival tissue; modifying the 3-D digital mesh to generate a digital mesh dentition model by: (i) processing the digital mesh and automatically detecting one or more initial bracket positions from the acquired mesh; (ii) processing the initial bracket positions to identify bracket areas for braces that lie against tooth surfaces; (iii) identifying one or more brace wires extending between brackets; (iv) removing one or more brackets and one or more wires from the dentition model; (v) forming a reconstructed tooth surface within the digital mesh dentition model where the one or more brackets have been removed; and displaying, storing, or transmitting over a network to another computer, the modified 3-D digital mesh dentition model.
- FIG. 1 is a schematic diagram that shows components of an imaging apparatus for surface contour imaging of a patient's teeth and related structures.
- FIG. 2 shows schematically how patterned light is used for obtaining surface contour information using a handheld camera or other portable imaging device.
- FIG. 3 shows an example of surface imaging using a pattern with multiple lines of light.
- FIG. 4 shows a point cloud generated from structured light imaging, such as that shown in FIG. 3 .
- FIG. 5 shows a polygon mesh in the simple form of a triangular mesh.
- FIG. 6 A is a logic flow diagram that shows a hybrid sequence for mesh segmentation according to an embodiment of the present disclosure.
- FIG. 6 B is a logic flow diagram that shows a workflow sequence for hybrid segmentation of the tooth according to an embodiment of the present disclosure.
- FIG. 7 A shows an example of a poorly segmented tooth.
- FIG. 7 B shows an example of an improved segmentation.
- FIG. 8 A shows an example of a seed line trace pattern.
- FIG. 8 B shows an example of a block line trace pattern.
- FIGS. 9 A, 9 B and 9 C show operator interface screens for review and entry of markup instructions for refining tooth mesh segmentation processing according to certain embodiments of the present disclosure.
- FIG. 10 is a logic flow diagram that shows a sequence for bracket removal from the tooth mesh surface according to an exemplary embodiment of the application.
- FIG. 11 shows an example of a dentition mesh containing teeth, brackets and gingival.
- FIG. 12 is a diagram that shows exemplary resultant separated teeth from a 3D dentition mesh according to an exemplary embodiment of the application.
- FIGS. 13 A- 13 C shows an example of removing a bracket from a tooth surface of a 3D dentition mesh and reconstructing the tooth surface afterwards.
- FIGS. 13 D and 13 E are diagrams that show a hole on tooth mesh surface where a bracket is removed and an initial patch approximated to fill the hole.
- FIG. 13 F is a diagram that shows an initial arrangement of triangles in a tooth surface mesh patch and a modified arrangement of triangles for a tooth surface mesh patch.
- FIG. 13 G shows an exemplary corrected 3D dentition mesh.
- FIG. 14 is a logic flow diagram that shows an exemplary sequence for automatic braces and brackets detection and removal by processing logic according to an embodiment of the present disclosure.
- FIG. 15 is a logic flow diagram showing a process for bracket area detection.
- FIG. 16 shows images for a sequence that follows steps given in FIG. 15 .
- FIG. 17 shows exemplary coarse brackets obtained using the described sequence.
- FIG. 18 shows braces wire detection.
- FIG. 19 shows an arrangement of vertices for mask generation.
- FIG. 20 shows the pruning operation for masks that can inaccurately extend to the opposite side in schematic representation.
- FIG. 21 shows a post-processing sequence
- FIG. 22 shows an exemplary Fast Marching process.
- FIG. 23 shows exemplary Fast March computation for arrival time from different seed-points along mask boundaries.
- FIG. 24 shows results of using a sequence of different approaches for refinement of bracket regions according to an embodiment of the present disclosure.
- FIG. 25 shows steps of an optional refinement of bracket regions using a convex hull computation.
- FIG. 26 shows fine tuned bracket regions obtained using the described sequence.
- FIG. 27 shows the recovered tooth surface following bracket removal.
- FIG. 28 is a logic flow diagram that shows a sequence for bracket removal from the tooth mesh surface according to another exemplary embodiment of the application.
- FIG. 29 shows an operator interface screen embodiment for review and entry of delineation instructions for separating brackets from tooth mesh according to one exemplary embodiment of the application.
- FIG. 29 also shows an example of a closed contour or snake encircling a bracket.
- FIG. 30 shows an example of highlighted mesh vertices within a closed contour.
- FIG. 31 shows an example of a reconstructed tooth surface after the bracket is removed.
- FIGS. 32 - 34 are diagrams that shows respectively, an example of dentition model with brackets, the same dentition model with brackets identified, and reconstructed teeth after brackets are removed according to one exemplary embodiment of the application.
- FIG. 35 A is a diagram that shows an example of a dentition mesh containing teeth, bridged brackets and gingival tissue.
- FIG. 35 B is a diagram that shows an example dentition mesh with bridges (e.g., wires) between brackets broken according to exemplary embodiments of the application.
- bridges e.g., wires
- FIG. 35 C is a diagram that shows an example dentition mesh illustrating detection of bridges (e.g., wires).
- FIG. 36 shows example results of bracket removal and surface reconstruction after breaking the bridge wires according to exemplary embodiments of the application.
- FIG. 37 is a logic flow diagram that shows a sequence for bridged bracket removal from the tooth mesh surface according to an embodiment of the present disclosure.
- FIG. 38 is a logic flow diagram that shows a sequence for bridged bracket removal from the tooth mesh surface according to another embodiment of the present disclosure.
- signal communication means that two or more devices and/or components are capable of communicating with each other via signals that travel over some type of signal path.
- Signal communication may be wired or wireless.
- the signals may be communication, power, data, or energy signals which may communicate information, power, and/or energy from a first device and/or component to a second device and/or component along a signal path between the first device and/or component and second device and/or component.
- the signal paths may include physical, electrical, magnetic, electromagnetic, optical, wired, and/or wireless connections between the first device and/or component and second device and/or component.
- the signal paths may also include additional devices and/or components between the first device and/or component and second device and/or component.
- pixel and “voxel” may be used interchangeably to describe an individual digital image data element, that is, a single value representing a measured image signal intensity.
- an individual digital image data element is referred to as a voxel for 3-dimensional or volume images and a pixel for 2-dimensional (2-D) images.
- voxel and pixel can generally be considered equivalent, describing an image elemental datum that is capable of having a range of numerical values.
- Voxels and pixels have attributes of both spatial location and image data code value.
- Patterned light is used to indicate light that has a predetermined spatial pattern, such that the light has one or more features such as one or more discernable parallel lines, curves, a grid or checkerboard pattern, or other features having areas of light separated by areas without illumination.
- the phrases “patterned light” and “structured light” are considered to be equivalent, both used to identify the light that is projected onto the head of the patient in order to derive contour image data.
- the terms “viewer”, “operator”, and “user” are considered to be equivalent and refer to the viewing practitioner, technician, or other person who views and manipulates a contour image that is formed from a combination of multiple structured, light images on a display monitor.
- a “viewer instruction”, “operator instruction”, or “operator command” can be obtained from explicit commands entered by the viewer or may be implicitly obtained or derived based on some other user action, such as making an equipment setting, for example.
- some other user action such as making an equipment setting, for example.
- the terms “command” and “instruction” may be used interchangeably to refer to an operator entry.
- a single projected line of light is considered a “one dimensional” pattern, since the line has an almost negligible width, such as when projected from a line laser, and has a length that is its predominant dimension.
- Two or more of such lines projected side by side, either simultaneously or in a scanned arrangement, provide a two-dimensional pattern.
- lines of light can be linear, curved or three-dimensional.
- 3-D model may be used synonymously in the context of the present disclosure.
- the dense point cloud is formed using techniques familiar to those skilled in the volume imaging arts for forming a point cloud and relates generally to methods that identify, from the point cloud, vertex points corresponding to surface features.
- the dense point cloud is thus generated using the reconstructed contour data from one or more reflectance images.
- Dense point cloud information serves as the basis for a polygon model at high density for the teeth and gum surface.
- geometric primitive refers to basic 2-D geometric shapes that can be entered by the operator in order to indicate areas of an image.
- geometric primitives can include lines, curves, points, and other open shapes, as well as closed shapes that can be formed by the operator, such as circles, closed curves, rectangles and squares, polygons, and the like.
- Embodiments of the present disclosure provide exemplary methods and/or apparatus that can help to eliminate the need for multiple CBCT scans for visualization of tooth and jaw structures.
- Exemplary methods and/or apparatus embodiments can be used to combine a single CBCT volume with optical intraoral scans that have the capability of tracking the root position at various stages of orthodontic treatment, for example.
- the intraoral scans are segmented so that exposed portions, such as individual tooth crowns, from the intraoral scan can be aligned with the individual tooth and root structure segmented from the CBCT volume.
- FIG. 1 is a schematic diagram showing an imaging apparatus 70 for projecting and imaging using structured light patterns 46 .
- Imaging apparatus 70 uses a handheld camera 24 for image acquisition according to an embodiment of the present disclosure.
- a control logic processor 80 or other type of computer that may be part of camera 24 controls the operation of an illumination array 10 that generates the structured light and controls operation of an imaging sensor array 30 .
- Image data from surface 20 is obtained from imaging sensor array 30 and stored in a memory 72 .
- Control logic processor 80 in signal communication with camera 24 components that acquire the image, processes the received image data and stores the mapping in memory 72 .
- the resulting image from memory 72 is then optionally rendered and displayed on a display 74 .
- Memory 72 may also include a display buffer for temporarily storing display 74 image content.
- a pattern of lines is projected from illumination array 10 toward the surface of an object from a given angle.
- the projected pattern from the surface is then viewed from another angle as a contour image, taking advantage of triangulation in order to analyze surface information based on the appearance of contour lines.
- Phase shifting in which the projected pattern is incrementally shifted spatially for obtaining additional measurements at the new locations, is typically applied as part of structured light projection imaging, used in order to complete the contour mapping of the surface and to increase overall resolution in the contour image.
- FIG. 2 shows, with the example of a single line of light L, how patterned light is used for obtaining surface contour information using a handheld camera or other portable imaging device.
- a mapping is obtained as an illumination array 10 directs a pattern of light onto a surface 20 and a corresponding image of a line L′ is formed on an imaging sensor array 30 .
- Each pixel 32 on imaging sensor array 30 maps to a corresponding pixel 12 on illumination array 10 according to modulation by surface 20 . Shifts in pixel position, as represented in FIG. 2 , yield useful information about the contour of surface 20 . It can be appreciated that the basic pattern shown in FIG.
- Illumination array 10 can utilize any of a number of types of arrays used for light modulation, such as a liquid crystal array or digital micromirror array, such as that provided using the Digital Light Processor or DLP device from Texas Instruments, Dallas, TX This type of spatial light modulator is used in the illumination path to change the light pattern as needed for the mapping sequence.
- the image of the contour line on the camera simultaneously locates a number of surface points of the imaged object. This can speed the process of gathering many sample points, while the plane of light (and usually also the receiving camera) is laterally moved in order to “paint” some or all of the exterior surface of the object with the plane of light.
- FIG. 3 shows surface imaging using a pattern with multiple lines of light. Incremental shifting of the line pattern and other techniques help to compensate for inaccuracies and confusion that can result from abrupt transitions along the surface, whereby it can be difficult to positively identify the segments that correspond to each projected line. In FIG. 3 , for example, it can be difficult to determine whether line segment 16 is from the same line of illumination as line segment 18 or adjacent line segment 19 .
- FIG. 4 shows a dense point cloud 50 generated from a structured light imaging apparatus, CS 3500 3-D camera made by Carestream Heath, Inc., Rochester NY, USA, using results from patterned illumination such as that shown in FIG.
- the point cloud 50 models physical location of sampled points on tooth surfaces and other intraoral surfaces or, more generally, of surfaces of a real-world object. Variable resolution can be obtained.
- the example of FIG. 4 shows an exemplary 100 micron resolution.
- the points in the point cloud represent actual, measured points on the three dimensional surface of an object.
- the surface structure can be approximated from the point cloud representation by forming a polygon mesh, in which adjacent vertices are connected by line segments. For a vertex, its adjacent vertices are those vertices closest to the vertex in terms of Euclidean distance.
- FIG. 5 shows a 3-D polygon mesh model 60 in the simple form of a triangular mesh.
- a triangular mesh forms a basic mesh structure that can be generated from a point cloud and used as a digital model to represent a 3-D object by its approximate surface shape, in the form of triangular plane segments sharing adjacent boundaries.
- Methods and apparatus for forming a polygon mesh model, such as a triangular mesh or more complex mesh structure, are well known to those skilled in the contour imaging arts.
- the polygon unit of the mesh model, and relationships between neighboring polygons, can be used in embodiments of the present disclosure to extract features (e.g., curvatures, minimum curvatures, edges, spatial relations, etc.) at teeth boundaries.
- segmentation of individual components of the image content from a digital model can be of value to the dental practitioner in various procedures, including orthodontic treatment and preparation of crowns, implants, and other prosthetic devices, for example.
- Various methods have been proposed and demonstrated for mesh-based segmentation of teeth from gums and of teeth from each other.
- drawbacks of conventional segmentation solutions include requirements for a significant level of operator skill and a high degree of computational complexity.
- Conventional approaches to the problem of segmenting tooth components and other dentition features have yielded disappointing results in many cases.
- Exemplary method and apparatus embodiments address such problems with segmentation that can utilize the polygonal mesh data as a type of source digital model and can operate in more than one stage: e.g., first, performing an automated segmentation that can provide at least a close or coarse approximation of the needed segmentation of the digital model; and second, allowing operator interactions to improve, correct or clean up observed errors and inconsistencies in the automated results, which can yield highly accurate results that are difficult to achieve in a purely automated manner without significant requirements on operator time or skill level or on needed computer resources.
- This hybrid approach in exemplary method and apparatus embodiments can help to combine computing and image processing power with operator perception to check, correct, and refine results of automated processing.
- the logic flow diagram of FIG. 6 A shows a hybrid sequence for tooth mesh segmentation and generation of a digital model to identify individual features or intraoral components such as teeth from within the mouth according to an exemplary embodiment of the present disclosure.
- an image acquisition step S 100 a plurality of structured light images of the patient's dentition are captured, providing a set of contour images for processing.
- a point cloud generation step S 110 then generates a point cloud of the patient's dentition using the set of contour images.
- a polygon mesh generation step S 120 forms a polygon mesh by connecting adjacent points from point cloud results.
- a triangular mesh provides one type of polygon mesh that can be readily generated for approximating a surface contour; more complex polygon mesh configurations can alternately be used.
- segmentation step S 130 can be executed.
- segmentation step S 130 can distinguish teeth from gum tissue, as well as distinguishing one tooth from another. Segmentation results can then be displayed, showing the results of this initial, automated segmentation processing.
- the automated segmentation step S 130 can provide an intermediate image.
- segmentation step S 130 can perform the bulk of segmentation processing, but can further benefit from operator review and refinements of results.
- segmentation step S 130 can use any of a number of known segmentation techniques, such as fast-marching watershed algorithms, so-called snake-based segmentation, and other methods known to those skilled in the imaging arts, as noted earlier.
- FIG. 6 A also shows an optional repeat loop that can enable viewer interaction with the intermediate image for refining the results of the automated segmentation processing, for example, using the basic apparatus shown in FIG. 1 .
- An accept operator instructions step S 140 can be executed, during which the viewer indicates, on the displayed results, seed points, seed lines, block lines, boundary features, or other markings that identify one or more distinct features of the segmentation results to allow further segmentation refinement and processing.
- Viewer markup instructions cause segmentation step S 130 to be executed at least a second time, this second time using input markup(s) from entered viewer instructions. It can be appreciated that different segmentation algorithms can be applied at various stages of automated or manual processing. Final results of segmentation processing can be displayed, stored, and transmitted between computers, such as over a wired or wireless network, for example.
- tooth and gum partitioning can be automated.
- tooth and gum partitioning can use an automated curvature-based method that computes curvature of vertices in the mesh, and then uses a thresholding algorithm to identify margin vertices having large negative curvature.
- color-based segmentation can be used for tooth segmentation from the gums. This type of method can obtain average hue values from regions of the image and calculate threshold values that partition image content.
- FIG. 6 B An exemplary embodiment of workflow for the hybrid tooth segmentation system is depicted in the logic flow diagram of FIG. 6 B .
- the control logic processor 80 ( FIG. 1 ) initiates an automated segmentation step S 202 in which a fully automatic tooth segmentation tool is evoked to delineate teeth and gum regions and delineate individual teeth regions.
- the fully automatic tooth segmentation tool employs exemplary algorithms such as active contour models published in the literature or otherwise well-known to those skilled in the image processing arts.
- the delineation of teeth effectively produces individually segmented teeth; however, these generated teeth may contain poorly segmented intraoral components.
- a first checking step S 204 then checks for poorly segmented intraoral components.
- Checking for incorrect or incomplete segmentation in step S 204 can be accomplished either computationally, such as by applying trained artificial intelligence algorithms to the segmentation results, or by viewer interaction, such as following visual inspection by the viewer.
- FIG. 7 A shows an exemplary poorly segmented or mis-segmented tooth 302 . As shown in FIG. 7 A , a segmented tooth boundary 306 is not aligned with an actual tooth boundary 308 .
- a primary assisted segmentation step S 206 executes, activating a segmentation procedure that is also automated, but allows some level of operator adjustment.
- Primary assisted segmentation step S 206 applies an algorithm for segmentation that allows operator adjustment of one or more parameters in a parameter adjustment step S 210 .
- Another checking step S 208 executes to determine if additional segmentation processing is needed.
- the adjustable parameter can be altered computationally or explicitly by an operator instruction in step S 210 . Subsequent figures show an exemplary operator interface for parameter adjustment.
- An exemplary algorithm employed in primary assisted segmentation Step S 206 can be a well-known technique, such as the mesh minimum curvature-based segmentation method.
- the adjustable parameter can be the threshold value of the curvature.
- the delineation of teeth performed in Step S 206 may still produce poorly segmented intraoral components or features, so that a repeated segmentation process is helpful.
- the checking of poor segmentation in step S 208 can be accomplished either computationally, such as by applying artificial intelligence algorithms to the segmentation results, or more directly, by visual inspection performed by the user.
- the hybrid tooth segmentation system optionally allows the user to add exemplary geometric primitives such as seed lines on the tooth region and add blocking lines between the teeth or between the teeth and gum to aid the tooth segmentation process.
- FIG. 8 A shows an exemplary seed line 406 for marking a tooth, added to a mesh image 62 .
- FIG. 8 B shows an exemplary block line 408 for indicating space between two teeth, added to a mesh image 62 .
- Step S 206 , Step S 208 and Step S 210 in the FIG. 6 B sequence constitute an exemplary primary segmentation loop 54 that follows the fully automatic segmentation of step S 202 and checking step S 204 .
- This exemplary primary segmentation loop 54 is intended to correct segmentation errors from the fully automated segmentation of automated segmentation step S 202 , as identified in step S 204 .
- Exemplary primary segmentation loop 54 can be executed one or more times, as needed. When exemplary primary segmentation loop 54 is successful, segmentation can be complete.
- an exemplary secondary segmentation loop 56 can be used to provide more interactive segmentation approaches.
- the secondary segmentation loop 56 can include an interactive segmentation step S 212 , another checking step S 214 , and an operator markup step S 216 .
- Interactive segmentation step S 212 can activate a segmentation process that works with the operator for indicating areas of the image to be segmented from other areas.
- Interactive segmentation step S 212 can have an automated sequence, implemented by an exemplary algorithm such as a “fast march” method known to those skilled in the image segmentation arts.
- Step S 212 may require population of the tooth region images by operator-entered seeds or seed lines or other types of geometric primitives before activation or during processing.
- seed lines or other features can be automatically generated in Step S 100 , S 110 and S 120 when the dentition mesh is entered into the system for optional operator adjustment (e.g., subsequent operations such as secondary segmentation loop 56 or Step 212 ).
- the features, seeds or seed lines can be added to the segmentation process in operator markup Step S 216 by the user.
- the results from Step S 212 are subject to inspection by the user in Step S 216 .
- Results from the hybrid automated/interactive segmentation processing can then be displayed in a display step S 220 , as well as stored and transmitted to another computer.
- some exemplary methods and apparatus of the present disclosure provide a hybrid tooth segmentation that provides the benefits of interactive segmentation with human-machine synergy.
- FIGS. 9 A- 9 C show operator interface screens 52 for portions of a sequence for review and entry of markup instructions for refining mesh segmentation processing according to certain exemplary embodiments of the present disclosure.
- Interim mesh segmentation results are shown in a display area 86 on screen 52 .
- a number of controls 90 for adjustment of the segmentation process are available, such as an adjustment control 84 for setting a level for overall aggressiveness or other parameter or characteristic of the segmentation processing algorithm.
- Optional selection controls 88 allow the viewer to specify one or more segmentation algorithms to be applied. This gives the operator an opportunity to assess whether one particular type of segmentation algorithm or another appear to be more successful in performing the segmentation task for the given mesh digital model. The operator can compare results against the original and adjust parameters to view results of successive segmentation attempts, with and without operator markup.
- FIG. 9 A also shows a trace pattern 96 that is entered as an operator seed line instruction for correcting or refining segmentation processing, as was shown previously with respect to FIG. 8 A .
- an operator mark in the form of trace pattern 96 or other arbitrary marking/geometric can be used to provide seed points that indicate a specific feature for segmentation, such as a molar or other tooth feature that may be difficult to process for conventional segmentation routines. Seed marks can then be used as input to a fast marching algorithm or other algorithm type, as described previously. In some cases, for example, adjacent teeth may not be accurately segmented with respect to each other; operator markup can provide useful guidance for segmentation processing where standard segmentation logic does not perform well. As FIG.
- FIG. 9 A shows, the operator can have controls 90 available that allow the entered markup to be cleared or provided to the segmentation processor.
- FIG. 9 B shows, color or shading can be used to differentiate various teeth or other structures identified by segmentation. Additional controls 90 can also be used to display individual segmented elements, such as individual teeth, for example.
- FIG. 9 C highlights, in some exemplary embodiments, individual controls 90 can be used individually or in combination.
- segmentation of individual teeth from each other can use curvature thresholds to compute margin and border vertices, then use various growth techniques to define the bounds of each tooth relative to margin detection.
- controls 90 can include, but are not limited to enter/adjust seed or boundary geometries, enter/adjust selected segmentation procedures, enter/adjust number of objects to segment, subdivide selected object, modify segmented object display, etc.
- FIG. 10 shows an exemplary embodiment of a workflow for bracket removal from a dentition 3D mesh according to an embodiment of the present disclosure.
- a virtual or digital 3D dentition mesh model is obtained in an acquisition step S 1002 .
- a digital 3D dentition mesh model can be obtained by using an intraoral scanner that employs structured light.
- FIG. 11 is a diagram that shows an exemplary 3D dentition mesh that can be acquired in step S 1002 of FIG. 10 .
- 3D dentition mesh 1100 can include brackets 1102 , gingival tissue 1104 and teeth 1106 .
- a result from the exemplary workflow process of FIG. 10 will be a 3D dentition mesh including the teeth 1106 and gingival tissue 1104 from the 3D dentition mesh 1100 , but without the brackets 1102 and tooth surfaces previously covered by brackets 1102 and with the tooth surfaces accurately reconstructed.
- separation steps 1004 and 1006 constitute a tooth segmentation method for an obtained dentition 3D mesh.
- steps S 1004 and S 1006 can be implemented by similar steps of a hybrid sequence for tooth mesh segmentation depicted in FIG. 6 A .
- steps S 1004 and S 1006 can be implemented by similar steps of a hybrid tooth segmentation method or system depicted in FIG. 6 B . Segmentation distinguishes each tooth from its neighboring teeth and from adjacent gingival tissue.
- brackets 1102 are automatically removed from the 3D dentition mesh 1100 (e.g., tooth surfaces) in a removal step S 1008 .
- the separated (or segmented) teeth resulting from step S 1006 can individually undergo bracket removal and surface reconstruction described hereafter.
- FIG. 12 is a diagram that shows exemplary resultant separated teeth 1202 contained within the 3D dentition mesh 1100 .
- each individually segmented tooth (or crown) is examined and processed.
- An exemplary segmented tooth 1202 with bracket 1302 to be removed is shown in FIG. 13 A .
- an automatic bracket removal algorithm first detects boundaries of the bracket 1302 .
- bracket boundary detection can use an automated curvature-based algorithm that detects and computes the curvatures of vertices in the mesh of tooth surfaces, and then uses a thresholding algorithm to identify margin vertices that have large negative curvature values, indicative of a high degree of curvature.
- FIG. 13 A is a diagram that shows an exemplary segmented tooth 1202 with bracket 1302 removed.
- small white patches can be present in the bracket hole 1304 ; these white patches do not belong to the bracket 1302 itself, but can be other artifacts behind the original bracket. These artifacts can become visible after the bracket 1302 has been removed from the 3D dentition mesh 1100 by an automatic bracket removal algorithm.
- a reconstruction step S 1010 tooth surfaces of the segmented tooth 1202 having the bracket removed are automatically reconstructed.
- Various approaches known to those skilled in the imaging arts can be used to fill holes in the 3D dentition mesh 1100 .
- An exemplary segmented tooth 1202 having automatically reconstructed tooth surface 1306 is shown in FIG. 13 C .
- hole-filling procedures e.g., tooth or crown surface reconstruction
- FIG. 13 D schematically shows a part of the 3D dentition mesh 1100 forming a 3D crown mesh surface after mesh portions representing a bracket are removed.
- a closed polygon 1303 ′ represents a boundary of the (removed) bracket.
- a region 1308 enclosed by the closed polygon 1303 ′ is the gap or hole left by bracket removal.
- an initial patch is generated to fill the tooth surface or hole of region 1308 (e.g., within the closed polygon 1303 ′).
- the initial patch contains a plurality of triangles 1310 arranged in an exemplary prescribed pattern such as one formed by connecting vertices in the closed polygon 1303 ′ to form the pattern shown in FIG. 13 E .
- polygons such as triangles 1310 of the initial patch can be further modified or optimized.
- One exemplary procedure of modifying or optimally arranging the triangles 1310 is illustrated in FIG. 13 F where four points A, B, C, and D form two triangles ABD and CDB in the triangles 1310 , which are rearranged to become triangles ABC and CDA in an improved set of triangles 1310 ′.
- An improved triangle arrangement can reduce or avoid long, thin triangles.
- the 3D mesh with the initial patch can be smoothed to obtain better quality.
- the second part of step S 1010 can correct positions of points created in the initial patch using local information globally.
- the 3D mesh including the initial patch e.g., triangles 1310 , 1310 ′ within the hole of polygon 1303 ′
- the surrounding regions, such as triangles 1312 surrounding (or nearby) the hole 1308 ′ in FIG. 13 D can be smoothed using a Laplacian smoothing method that adjusts the location of each mesh vertex to the geometric center of its neighbor vertices.
- the guidance vector field on a discrete triangle mesh as used in Wei Zhao's method is defined as a piecewise constant vector function whose domain is the set of all points on the mesh surface. The constant vector is defined for each triangle and this vector is coplanar with the triangle.
- a display step S 1012 of FIG. 10 the exemplary segmented tooth 1202 having automatically reconstructed tooth surface 1306 (see FIG. 13 C ) can be displayed.
- steps S 1008 , S 1010 and S 1012 can be repeatedly performed until all brackets are removed from 3D dentition mesh 1100 .
- the resultant corrected 3D dentition mesh 1100 can be displayed in step S 1012 after each additional segmented tooth surface is corrected.
- steps S 1008 and S 1010 can be performed for all teeth in the 3D dentition mesh 1100 , before the resultant corrected 3D dentition mesh 1100 is displayed in step 1012 .
- FIG. 13 G shows an exemplary corrected 3D dentition mesh 1316 .
- Certain exemplary method and/or apparatus embodiments can provide automatic braces detection and removal by initial (e.g., coarse) bracket detection, subsequent wire detection, and refinement of detected (e.g., separated) initial brackets, which can then be removed from the initial 3D mesh and subsequently filled by various surface reconstruction techniques.
- a coarse bracket detection step S 1302 provides estimated positions of brackets, using an approach such as that described subsequently.
- a brace wires detection step S 1304 then detects connecting wires that extend across the bracket region.
- a masks generation step S 1308 generates masks for the brackets; these masks narrow the search area for detection.
- a processing step S 1310 provides pruning and other morphological operations for further defining the masks.
- a Fast March application step S 1320 executes a fast march algorithm according to the defined mask region.
- a refinement step S 1330 performs the necessary refinement of detected bracket areas or regions using morphological operators.
- a fine tuning step S 1340 generates the fine-tuned bracket regions that are then used for removal steps.
- Coarse bracket detection in step S 1302 can proceed as described in the flow diagram of FIG. 15 and as shown visually in the sequence of FIG. 16 .
- a computation step S 1306 the system computes a parabola 502 that is a suitable fit for the imaged dentition. This is typically executed from image content in a top view image 500 as shown, using curvature detection logic. Parabola 502 can be traced along the edges of teeth in the arch using the imaged content. Given this processing, in a side detection step S 1312 , a buccal side 504 or, alternately, the opposite lingual side of the arch is then identified.
- bracket area 506 detection uses the following general sequence, repeated for points along parabola 502 :
- a decision step S 1328 determines whether or not post treatment is needed in order to correct for processing errors. If post treatment is not required, bracket areas have been satisfactorily defined. If post treatment is required, further processing is applied in a false detection correction step S 1332 to remove false positives and in a clustering step S 1344 to effect further clustering of bracket areas that are in proximity and that can be assumed to belong to the same bracket 510 .
- FIG. 17 shows exemplary coarse brackets 510 obtained using the described coarse bracket detection sequence of FIG. 15 .
- Brace wires detection step S 1304 from the FIG. 14 sequence can proceed as shown in FIG. 18 and as described following.
- Coarse brackets 510 may be connected by brace wires 512 . Processing can detect wire extending from each bracket region. It is useful to remove these wires in order to obtain improved bracket removal.
- processing can perform a nearest neighbor search within a suitable radius, such as within an exemplary 5 mm radius, resulting in a set of neighbor vertices VN. Processing then checks the normal of each of the vertices in VN.
- the detected wires can facilitate identification of the individual brackets. If it is determined that the normal for at least one vertex in VN points to the opposite direction of the normal of the vertex V (e.g. if the dot product of the two normal vectors ⁇ 0.9), then V is considered a candidate vertex on the wire (or bridge). This can be measured, for example, because there is space between the wire feature and the tooth. This procedure can be applied to the entire mesh, resulting in a set that has a number of candidate vertices.
- the set of candidate vertices is used to compute a plurality of connected regions.
- Each of the connected regions can be analyzed using a shape detection algorithm, such as principal component analysis PCA, familiar to those skilled in the imaging arts and used for shape detection, such as wire detection.
- a shape detection algorithm such as principal component analysis PCA, familiar to those skilled in the imaging arts and used for shape detection, such as wire detection.
- FIG. 18 shows results of wire detection for wires 512 extending between brackets. These detected wires can then be used to algorithmically identify and separate connected brackets.
- an initial mask can be generated for each individual coarse bracket. These initial masks can be helpful for narrowing the search area in Fast Marching brackets detection. In practice, a proper initial mask should be, adequately large enough to cover all the components (base, pad, slots, hook, band, etc.) that belong to a bracket.
- Generating and processing initial masks from steps S 1308 and S 1310 in FIG. 14 can be executed as follows. Referring to the schematic diagram of FIG. 19 , this processing can generate a mask for each bracket. The mask is used to define the region of interest (ROI) for subsequent fast march bracket detection.
- ROI region of interest
- Processing for mask generation can use the following sequence, with reference to FIG. 19 :
- centroid of each mask 520 is connected to each neighbor along the arch, as represented in flattened form in FIG. 19 .
- FIG. 20 shows the pruning operation for masks that inaccurately extend to the opposite side in schematic representation at images 530 . Pruning results are shown in the example of image 532 . Pruning for masks that inaccurately extend across teeth, as shown in image 540 , is shown in image 542 .
- the bi-normal bn can be defined as the vector from a bracket's own center to that of the next bracket in the series that is formed by sorting all brackets that lie along the dental arch from one side to another.
- the cross product of the z-axis and bi-normal can be used to generate its normal as depicted in FIG. 19 , showing the z-axis, normal n, and bi-normal bn of each bracket.
- An image 550 shows encircled gaps 556 that can be filled in order to complete masked regions. The remaining vertices after pruning are dilated to connect discontinuous regions and to fill regions that may have been inaccurately pruned. Dilation can be followed by an erosion process to remove regions of the mask lying between the teeth, as shown in encircled areas 552 , 554 .
- An image 560 shows improvement to the encircled regions of image 550 .
- An image 580 shows the completed mask following both dilation and erosion processing.
- a Fast March algorithm can be applied within each mask, with boundaries of the mask used as seed vertices.
- the arrival time for seed vertices can be set to 0.
- the arrival time for vertices within the mask can be computed with the common Fast Marching process, as shown schematically in FIG. 22 .
- Fast March processing uses a weighting or cost function in order to determine the most likely path between vertices in each masked region.
- FIG. 22 shows different computations that can apply for paths between given vertices using Fast March methods.
- FIG. 23 shows exemplary Fast March computation for arrival time from different seed-points along mask boundaries using the Fast March method. Masked regions 590 are shown, with grayscale- or color-encoded arrival times used for comparison as shown in image 595 in FIG. 23 .
- the boundary of a bracket is characterized by a high absolute value of curvature.
- the Fast Marching algorithm applies a speed function in order to compute the weight assigned to each edge in the graph. For bracket removal, there is a need for reduced edge weights in flat regions and larger edge weight values in highly curved regions.
- the D normal value is approximate to the averaged normal curvature of v 0 and v 1 , times the distance S from v 0 and v 1 :
- the mean curvature can be used.
- the mean curvature is readily computed (as compared against a normal curvature) and operates without concern for possible differences in estimation for the propagating front stop at regions that are highly curved.
- the speed function is therefore defined as:
- W w normal ⁇ ( ⁇ m ⁇ e ⁇ a ⁇ n ⁇ ( v 0 ) + ⁇ m ⁇ e ⁇ a ⁇ n ⁇ ( v 1 ) 2 ) ⁇ S , wherein ⁇ mean is the mean curvature and w normal is a weight value.
- the speed function used for processing with masked Fast Marching can be defined as a normal difference of two neighbor vertices along the edge of an area being processed. Where vertices v 0 and v 1 are two neighboring vertices (that is, within nearest proximity of each other relative to the display medium), the normal difference is equal to the integration of normal curvature ⁇ normal in the geodesic line from vertex v 1 to v 2 . The normal difference is approximate to the average normal curvature of v 0 and v 1 , times a distance S from v 0 to v 1 .
- FIG. 24 shows results of using a sequence of different approaches for refinement of bracket regions according to an embodiment of the present disclosure.
- An image 600 shows fast marching results for a typical image having brackets and braces.
- An image 610 shows results of image thresholding, well known to those skilled in the imaging arts.
- An image 620 shows results of a dilation and fill process.
- An image 630 shows results following image erosion, using a maximum-sized region.
- FIG. 25 shows steps of an optional refinement of bracket regions using a convex hull computation.
- the following sequence can be used for convex hull processing:
- FIG. 26 shows the fine tuned bracket regions obtained using the described sequence.
- FIG. 27 shows the recovered tooth surface following bracket definition and removal by applying, to the results in FIG. 26 , the surface reconstruction process detailed in the preceding paragraphs and the sequence described with reference to FIGS. 13 A- 14 .
- FIG. 28 is a logic flow diagram that shows a workflow of another exemplary embodiment of the present disclosure for bracket removal on a 3D dentition mesh. Unlike the workflow shown in FIG. 10 , the workflow shown in FIG. 28 does not require tooth segmentation as a separate step.
- a 3D dentition mesh is received in an acquisition step S 1402 ; the received mesh contains teeth, brackets, and gingival tissue. Then, in an instruction step S 1404 , instructions are received from an operator regarding brackets in the 3D dentition mesh.
- FIG. 29 is a diagram that displays an exemplary graphical user interface (GUI) that allows the user to input information to identify brackets in the 3D dentition mesh.
- GUI graphical user interface
- one exemplary GUI interface 1500 enables nodes to be placed by the user for a ‘snake’ operation, which automatically encircles bracket 1502 boundaries, based on the entered nodes.
- An exemplary bracket boundary 1503 generated by the automated ‘snake’ operation is shown in FIG. 29 .
- the ‘snake’ is an active shape model that is frequently used in automatic object segmentation in image processing, for example by delineating an object outline from a possibly noisy 2D image.
- the active shape model of the snake is similar to that used in applications like object tracking, shape recognition, segmentation, edge detection and stereo matching. Methods using a snake active shape model or active contour model are well known to those skilled in the imaging arts.
- FIG. 30 shows vertices 1602 encircled by the boundary 1503 being highlighted in the 3D dentition mesh after the user presses the ‘run’ command button 1504 in FIG. 29 .
- Identified vertices 1602 are to be removed from the original 3D dentition mesh.
- the GUI 1500 can let the user inspect the intermediate results for vertices 1602 , and if satisfied, the user presses the ‘cut’ button 1506 .
- the vertices 1602 change their highlight (e.g., color, texture, etc.) to indicate that these vertex features are to be removed from the original 3D dentition mesh.
- pressing the ‘cut’ button 1506 causes processing to automatically remove the brackets from the teeth surface in a removal step S 1406 based on the operator instructions in step S 1404 .
- step S 1408 is performed when the user presses the ‘fill’ button 1506 in FIG. 29 to reconstruct tooth surfaces and remove any holes or gaps caused by bracket removal.
- Step S 1408 can be performed using known algorithms such as described herein with respect to FIG. 10 .
- FIG. 31 shows an example of a reconstructed tooth surface 1702 after the bracket is removed.
- the procedures shown in the FIG. 28 sequence can be performed tooth by tooth, on a small group of adjacent teeth, or on all teeth simultaneously with respect to the 3D dentition mesh.
- FIGS. 32 - 34 are diagrams that show sequential stages in the process leading to a complete, concurrent removal of all brackets from a 3D jaw mesh.
- FIG. 32 is a diagram that shows a 3D dentition mesh 1800 with teeth, brackets and gingival tissue.
- FIG. 33 is a diagram that shows the intermediate results of ‘snake’ cut operation with vertices 1802 that are to be removed shown in highlighted form.
- FIG. 34 is a diagram that shows each of the final reconstructed teeth surfaces 1806 after all brackets are removed and all fill operations are completed.
- FIG. 35 A is a diagram that shows another exemplary dentition model.
- dentition model 2100 includes brackets 2102 , gingival tissue 2104 , teeth 2106 and bridged brackets where a wire 2108 connects at least bracket 2110 and bracket 2112 .
- wires 2108 will connect all brackets 2102 .
- the wire 2108 can, once identified, be erased automatically or interactively according to exemplary methods and apparatus of the present disclosure.
- FIG. 36 an actual result 2204 for bridged brackets removal is shown.
- the surface reconstructed tooth 2210 and tooth 2212 in FIG. 36 correspond to bracket 2110 and bracket 2112 in FIG. 21 A before the brackets and wire 2108 are removed.
- FIG. 37 is a logic flow diagram that shows an exemplary sequence for bridged bracket removal from tooth mesh surfaces according to an embodiment of the present disclosure.
- a dentition model with bridged brackets is obtained in an acquisition step S 2302 , which is immediately followed by a cutting step S 2304 that includes automatically “breaking the bridge”.
- a cutting step S 2304 that includes automatically “breaking the bridge”.
- One exemplary detection embodiment that can be used to automatically break the bridge (or wire) is described as follows.
- a removal step S 2306 given a vertex V in the dentition mesh model, processing logic performs a nearest neighbor search with an exemplary 5 mm radius resulting in a set of neighbor vertices VN. As described in the preceding sections, the system checks the normal of each of the vertices V in set VN. If it is found that there is at least one vertex in VN whose normal points to the opposite direction of the normal of V (e.g. if these two normal vectors' dot product ⁇ 0.9), then vertex V is on the wire (or bridge). An exemplary bridge (wire) detection result 2118 resulting from step S 2306 is shown in FIG. 35 C . These vertices of the 3D detention mesh detected in step S 2306 (e.g., associated with the wires 2108 ) are excluded or removed from the 3D detention mesh in the subsequent removal step S 2306 and reconstruction step S 2308 .
- Removal step S 2306 employs either exemplary automatic or interactive methods to remove the disconnected brackets.
- the bracket removed tooth surface is reconstructed automatically in a reconstruction step S 2308 and the results are displayed for inspection in a display step S 2310 .
- steps S 2306 and S 2308 can be performed as described above for FIGS. 10 and 28 , respectively.
- FIG. 38 is a logic flow diagram that shows another exemplary method embodiment for bridged brackets removal.
- a dentition model with bridged brackets is acquired in an acquisition step S 2402 , which is immediately followed by an interaction step S 2404 of interactively “breaking the bridge”.
- interactive operation effectively erases the thin wires with the assistance from a human by selecting and deleting mesh vertices that belong to the thin wires in step S 2404 .
- step S 2404 can use a GUI with selectable operator actions to “clear”, “paint” (e.g., operator identify pixels showing wires), “auto paint”, “approve” (e.g., paint or auto paint), and “clear” to interactively break the bridges or remove the wires from the 3D dentition mesh based on the operator instructions.
- a removal step S 2406 employs either automatic or interactive method to remove the disconnected brackets as previously described.
- the bracket removed tooth surfaces can be reconstructed automatically in a reconstruction step S 2408 as previously described.
- the results are displayed for inspection in a display step S 2410 .
- bridged brackets can be removed and teeth surfaces restored by automatically identifying parts of a bracket and/or wire without human intervention in an obtained 3D dentition model by growing the identified parts into a region that covers the brackets and/or wires entirely (e.g., and preferably slightly beyond the brackets and/or wires boundaries). removing the region from the 3D dentition model surface, and restoring the removed region surfaces using hole filing techniques.
- hole filling can fill portions of gingival tissue in addition to tooth surface portions. Surface data of the patient that were previously acquired, such as from a dentition mesh model obtained before braces were applied, can be used to generate the reconstructed tooth surface.
- the present disclosure can use a computer program with stored instructions that control system functions for image acquisition and image data processing for image data that is stored and accessed from an electronic memory.
- a computer program of an embodiment of the present invention can be utilized by a suitable, general-purpose computer system, such as a personal computer or workstation that acts as an image processor, when provided with a suitable software program so that the processor operates to acquire, process, transmit, store, and display data as described herein.
- a suitable, general-purpose computer system such as a personal computer or workstation that acts as an image processor
- a suitable software program so that the processor operates to acquire, process, transmit, store, and display data as described herein.
- Many other types of computer systems architectures can be used to execute the computer program of the present invention, including an arrangement of networked processors, for example.
- the computer program for performing the method of the present invention may be stored in a computer readable storage medium.
- This medium may comprise, for example; magnetic storage media such as a magnetic disk such as a hard drive or removable device or magnetic tape; optical storage media such as an optical disc, optical tape, or machine readable optical encoding; solid state electronic storage devices such as random access memory (RAM), or read only memory (ROM); or any other physical device or medium employed to store a computer program.
- the computer program for performing the method of the present invention may also be stored on computer readable storage medium that is connected to the image processor by way of the internet or other network or communication medium. Those skilled in the image data processing arts will further readily recognize that the equivalent of such a computer program product may also be constructed in hardware.
- memory can refer to any type of temporary or more enduring data storage workspace used for storing and operating upon image data and accessible to a computer system, including a database.
- the memory could be non-volatile, using, for example, a long-term storage medium such as magnetic or optical storage. Alternately, the memory could be of a more volatile nature, using an electronic circuit, such as random-access memory (RAM) that is used as a temporary buffer or workspace by a microprocessor or other control logic processor device.
- Display data for example, is typically stored in a temporary storage buffer that is directly associated with a display device and is periodically refreshed as needed in order to provide displayed data.
- This temporary storage buffer can also be considered to be a memory, as the term is used in the present disclosure.
- Memory is also used as the data workspace for executing and storing intermediate and final results of calculations and other processing.
- Computer-accessible memory can be volatile, non-volatile, or a hybrid combination of volatile and non-volatile types.
- the computer program product of the present disclosure may make use of various image manipulation algorithms and processes that are well known. It will be further understood that the computer program product embodiment of the present invention may embody algorithms and processes not specifically shown or described herein that are useful for implementation. Such algorithms and processes may include conventional utilities that are within the ordinary skill of the image processing arts. Additional aspects of such algorithms and systems, and hardware and/or software for producing and otherwise processing the images or co-operating with the computer program product of the present invention, are not specifically shown or described herein and may be selected from such algorithms, systems, hardware, components and elements known in the art.
- the terms “a” or “an” are used, as is common in patent documents, to include one or more than one, independent of any other instances or usages of “at least one” or “one or more.”
- the term “or” is used to refer to a nonexclusive or, such that “A or B” includes “A but not B,” “B but not A,” and “A and B,” unless otherwise indicated.
- Certain exemplary method and/or apparatus embodiments can provide automatic braces detection and removal by initial (e.g., coarse) bracket detection, subsequent wire detection, and refinement of detected (e.g., separated) initial brackets, which can then be removed from the initial 3D mesh.
- initial bracket detection e.g., coarse
- subsequent wire detection e.g., refinement of detected (e.g., separated) initial brackets, which can then be removed from the initial 3D mesh.
- Exemplary embodiments according to the application can include various features described herein (individually or in combination).
Abstract
Description
-
- (i) A method described in the article “Snake-Based Segmentation of Teeth from Virtual Dental Casts” by Thomas Kronfeld et al. (in Computer-Aided Design & applications, 7(a), 2010) employs an active contour segmentation method that attempts to separate every tooth and gum surface in a single processing iteration. The approach that is described, however, is not a topology-independent method and can fail, particularly where there are missing teeth in the jaw mesh.
- (ii) An article entitled “Perception-based 3D Triangle Mesh Segmentation Using Fast Marching Watershed” by Page, D. L. et al. (in Proc. CVPI vol II 2003) describes using a Fast Marching Watershed method for mesh segmentation. The Fast Marching Watershed method that is described requires the user to enter seed points manually. The seed points must be placed at both sides of the contours of the regions under segmentation. The method then attempts to segment all regions in one step, using seed information. For jaw mesh segmentation, this type of method segments each tooth as well as the gum at the same time. This makes the method less desirable, because segmenting teeth from the gum region typically requires parameters and processing that differ from those needed for the task of segmenting teeth from each other. Using different segmentation strategies for different types of dentition components with alternate segmentation requirements would provide better performance.
- (iii) For support of his thesis, “Evaluation of software developed for automated segmentation of digital dental models”, J. M. Moon used a software tool that decomposed the segmentation process into two steps: separation of teeth from gingival structure and segmentation of whole arch structure into individual tooth objects. The software tool used in Moon's thesis finds maximum curvature in the mesh and requires the user to manually choose a curvature threshold to obtain margin vertices that are used for segmenting the tooth. The software also requires the user to manually edit margins in order to remove erroneous segmentation results. Directed to analysis of shape and positional characteristics, this software tool does not employ color information in the separation of teeth regions from the gum regions.
- (iv) U.S. Patent application 20030039389 A1 entitled “Manipulating a digital dentition model to form models of individual dentition components” by Jones, T. N. et al. discloses a method of separating portions of the dentition model representing the adjacent teeth.
Δf=div(h)f| ∂Ω =f*| ∂Ω
wherein f is an unknown scalar function;
is a Laplacian operator; h is the guidance vector field; div(h) is the divergence of h; and f* is a known scalar function providing the boundary condition. The guidance vector field on a discrete triangle mesh as used in Wei Zhao's method is defined as a piecewise constant vector function whose domain is the set of all points on the mesh surface. The constant vector is defined for each triangle and this vector is coplanar with the triangle.
-
- (i) Extend a normal outward toward the side from the generated
parabola 502; - (ii) Detect a maximum length of the extended normals within a local neighborhood, such as within a predetermined number of pixels or calculated measurement;
- (iii) Select nearby points on the mesh that lie within a predetermined distance from the detected maximum.
These substeps identify candidate bracket areas orregions 508 as shown in the example ofFIG. 16 . Thesecandidate areas 508 can be processed in order to more accurately identify bracket features that lie against the teeth and to distinguish each bracket from the corresponding tooth surface.
- (i) Extend a normal outward toward the side from the generated
-
- (i) Jaw mesh orientation. The z axis is orthogonal to the bite plane.
- (ii) Sorting. Brackets, separated by wire detection, in each dental arch are sorted and center, normal, and bi-normal features are computed for each bracket.
- (iii) Identification. Each bracket type is identified as either lingual or buccal, on back molar or on other teeth. A suitable radius is set for mask generation for each bracket.
- (iv) Radius search. A radius search is executed from the center of each initial bracket in order to generate an
initial mask 520 for each bracket. The mask should be large enough to contain the bracket.
-
- (i) Compute Dnormal, the dot product of the normal and bracket normal for each vertex:
D normal =<N vi ,N bracket> - wherein Nvi is the normal of vertex vb Nbracket is the bracket normal. (The notation <a,b> indicates dot product and can alternately be expressed as a·b.)
- (ii) Remove the vertices whose Dnormal value is below a predetermined threshold value (for example, below −0.1). This dot product value indicates vectors tending towards opposite directions.
- (i) Compute Dnormal, the dot product of the normal and bracket normal for each vertex:
-
- (i) Compute Dbinormal for each vertex:
D binormal =<N vi ,BN bracket>*Sgn(<Dir vi ,BN bracket>) - wherein Nvi is the normal of vertex vi; BNbracket is the binormal of the bracket; Dirvi is the direction from the bracket center to vertex vi; and
- Sgn(x) returns the +/− sign of (x).
- (ii) Remove vertices whose Dbinormal value is smaller than a threshold value (for example, smaller than −0.1).
- (i) Compute Dbinormal for each vertex:
wherein κmean is the mean curvature and wnormal is a weight value.
-
- (i) compute the boundary of a bracket region in the mesh, as shown in an
image 700; in the example shown, a large gap exists within the bracket region; - (ii) project the boundary vertices to the 2D PCA plane of the boundary as shown in an
image 710; - (iii) compute the convex hull in the PCA plane, as shown in an
image 720; - (iv) detect and record pairs of points that are connected, such as non-neighbor vertices as shown in an
image 730; - (v) connect paired vertices in the original 3D boundary with geodesic lines to form a 2-manifold convex hull, as shown in an
image 740.
The resulting convex hull connects the gap that appears inimage 700 and covers the full bracket.
- (i) compute the boundary of a bracket region in the mesh, as shown in an
Claims (19)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/555,797 US11896455B2 (en) | 2016-11-30 | 2021-12-20 | Method and system for braces removal from dentition mesh |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/US2016/064102 WO2018101923A1 (en) | 2016-11-30 | 2016-11-30 | Method and system for braces removal from dentition mesh |
US201916465565A | 2019-05-30 | 2019-05-30 | |
US17/555,797 US11896455B2 (en) | 2016-11-30 | 2021-12-20 | Method and system for braces removal from dentition mesh |
Related Parent Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2016/064102 Continuation WO2018101923A1 (en) | 2016-11-30 | 2016-11-30 | Method and system for braces removal from dentition mesh |
US16/465,565 Continuation US20200015936A1 (en) | 2016-11-30 | 2016-11-30 | Method and system for braces removal from dentition mesh |
Publications (2)
Publication Number | Publication Date |
---|---|
US20220233275A1 US20220233275A1 (en) | 2022-07-28 |
US11896455B2 true US11896455B2 (en) | 2024-02-13 |
Family
ID=57570446
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/465,565 Abandoned US20200015936A1 (en) | 2016-11-30 | 2016-11-30 | Method and system for braces removal from dentition mesh |
US17/555,797 Active 2037-01-15 US11896455B2 (en) | 2016-11-30 | 2021-12-20 | Method and system for braces removal from dentition mesh |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/465,565 Abandoned US20200015936A1 (en) | 2016-11-30 | 2016-11-30 | Method and system for braces removal from dentition mesh |
Country Status (7)
Country | Link |
---|---|
US (2) | US20200015936A1 (en) |
EP (1) | EP3547949B1 (en) |
JP (1) | JP2019536561A (en) |
KR (1) | KR20190087593A (en) |
CN (1) | CN110087577B (en) |
PL (1) | PL3547949T3 (en) |
WO (1) | WO2018101923A1 (en) |
Families Citing this family (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11559378B2 (en) | 2016-11-17 | 2023-01-24 | James R. Glidewell Dental Ceramics, Inc. | Scanning dental impressions |
US20200015936A1 (en) | 2016-11-30 | 2020-01-16 | Carestream Dental Technology Topco Limited | Method and system for braces removal from dentition mesh |
US11896452B2 (en) | 2017-03-16 | 2024-02-13 | Carestream Health, Inc. | Method for virtual setup with mixed dentition |
EP3668345A1 (en) * | 2017-08-17 | 2020-06-24 | Trophy | Stencil for intraoral surface scanning |
US20210200188A1 (en) * | 2018-10-23 | 2021-07-01 | Ormco Corporation | Systems and methods for designing and manufacturing an orthodontic appliance |
CN110269703B (en) * | 2019-06-18 | 2021-02-09 | 成都玻尔兹曼智贝科技有限公司 | Method for generating occlusion curve of mandibular tooth model |
US11622843B2 (en) | 2019-06-25 | 2023-04-11 | James R. Glidewell Dental Ceramics, Inc. | Processing digital dental impression |
US11534271B2 (en) | 2019-06-25 | 2022-12-27 | James R. Glidewell Dental Ceramics, Inc. | Processing CT scan of dental impression |
US11540906B2 (en) | 2019-06-25 | 2023-01-03 | James R. Glidewell Dental Ceramics, Inc. | Processing digital dental impression |
JP7303069B2 (en) * | 2019-08-28 | 2023-07-04 | ヤマハ発動機株式会社 | inspection equipment |
US11481974B2 (en) * | 2020-01-22 | 2022-10-25 | Vntana, Inc. | Mesh optimization for computer graphics |
US11544846B2 (en) | 2020-08-27 | 2023-01-03 | James R. Glidewell Dental Ceramics, Inc. | Out-of-view CT scan detection |
CN112215065B (en) * | 2020-09-04 | 2024-02-27 | 北京大学口腔医学院 | Automatic tooth jaw boundary feature recognition method |
US11475544B2 (en) * | 2020-10-16 | 2022-10-18 | Adobe Inc. | Automated braces removal from images |
EP4268195A1 (en) | 2020-12-23 | 2023-11-01 | Hirsch Dynamics Holding AG | Automatic creation of a virtual model and an orthodontic treatment plan |
US11055850B1 (en) * | 2021-01-06 | 2021-07-06 | Oxilio Ltd | Systems and methods for tooth segmentation |
CN112932697B (en) * | 2021-01-29 | 2022-05-24 | 正雅齿科科技(上海)有限公司 | Hard palate area identification method and system in dental model |
CN115365162A (en) * | 2022-08-22 | 2022-11-22 | 兰州理工大学 | Potato grading device based on machine vision and shape detection method |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030039389A1 (en) | 1997-06-20 | 2003-02-27 | Align Technology, Inc. | Manipulating a digital dentition model to form models of individual dentition components |
US20060093992A1 (en) | 2004-11-02 | 2006-05-04 | Huafeng Wen | Method and apparatus for manufacturing and constructing a physical dental arch model |
US20060134580A1 (en) | 2004-12-17 | 2006-06-22 | 3M Innovative Properties Company | RFID tracking of patient-specific orthodontic materials |
US20060134581A1 (en) | 2003-07-23 | 2006-06-22 | Orametrix, Inc. | Automatic crown and gingiva detection from three-dimensional virtual model of teeth |
US20070188601A1 (en) | 2006-02-13 | 2007-08-16 | Janos Rohaly | Three-channel camera systems with non-collinear apertures |
US20080248443A1 (en) * | 1997-06-20 | 2008-10-09 | Align Technology, Inc | Clinician review of an orthodontic treatment plan and appliance |
US20110004331A1 (en) | 2007-12-21 | 2011-01-06 | 3M Innovative Properties Company | Methods of preparing a virtual dentition model and fabricating a dental retainer therefrom |
US20140067334A1 (en) * | 2012-09-06 | 2014-03-06 | Align Technology Inc. | Method and a system usable in creating a subsequent dental appliance |
US20160004811A1 (en) * | 2014-07-01 | 2016-01-07 | 3M Innovative Properties Company | Detecting tooth wear using intra-oral 3d scans |
US20160199154A1 (en) | 2013-08-14 | 2016-07-14 | 3M Innovative Properties Company | An orthodontic bracket and a method of making an orthodontic bracket |
US20170105814A1 (en) | 2014-05-22 | 2017-04-20 | Industry-Academic-Cooperation Foundation Chosun University | Method of fabricating custom dental correction device, and custom dental correction device fabricated by same |
US20190159868A1 (en) | 2016-07-28 | 2019-05-30 | Carestream Dental Technology Topco Limited | Method and System for Dentition Mesh Braces Removal |
US20200015936A1 (en) | 2016-11-30 | 2020-01-16 | Carestream Dental Technology Topco Limited | Method and system for braces removal from dentition mesh |
Family Cites Families (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6648640B2 (en) * | 1999-11-30 | 2003-11-18 | Ora Metrix, Inc. | Interactive orthodontic care system based on intra-oral scanning of teeth |
US7347686B2 (en) * | 2002-01-22 | 2008-03-25 | Geodigm Corporation | Method and apparatus using a scanned image for marking bracket locations |
US8512037B2 (en) * | 2002-09-26 | 2013-08-20 | Ormco Corporation | Custom orthodontic appliance system and method |
US20040166462A1 (en) * | 2003-02-26 | 2004-08-26 | Align Technology, Inc. | Systems and methods for fabricating a dental template |
DE102004038136B4 (en) * | 2004-07-08 | 2019-06-13 | Sirona Dental Systems Gmbh | Method of constructing the surface of a three-dimensional data dental prosthesis |
US7916911B2 (en) * | 2007-02-26 | 2011-03-29 | Align Technology, Inc. | System and method for digital tooth imaging |
JP2010532681A (en) * | 2007-06-29 | 2010-10-14 | スリーエム イノベイティブ プロパティズ カンパニー | Video auxiliary boundary marking for dental models |
CN201235007Y (en) * | 2007-11-20 | 2009-05-13 | 孙轲 | Orthodontic bracket positioning mounting device |
CN101584608B (en) * | 2008-05-23 | 2012-09-05 | 哈尔滨理工大学 | Dental arch curve generator driven by motor |
DE102010002206B4 (en) * | 2010-02-22 | 2015-11-26 | Sirona Dental Systems Gmbh | Bracket system and method for planning and positioning a bracket system for correcting misaligned teeth |
EP2766304B1 (en) * | 2011-10-10 | 2018-12-05 | 3M Innovative Properties Company | Aerogels, calcined and crystalline articles and methods of making the same |
CN102609965B (en) * | 2012-02-13 | 2014-12-03 | 北京朗视仪器有限公司 | Data processing method of panoramagram generated by dental CBCT (cone beam computed tomography) |
CN203468765U (en) * | 2013-09-18 | 2014-03-12 | 蔡斌 | Oral-cavity orthodontic towing hook for enabling tooth to integrally move and orthodontic device |
EP2907476A1 (en) * | 2014-02-12 | 2015-08-19 | 3M Innovative Properties Company | A method of making a customized orthodontic bracket |
CN104083224B (en) * | 2014-07-04 | 2017-04-05 | 谭荣基 | Automatization's orthodontic bracket alignment system |
CN105147401B (en) * | 2015-08-04 | 2018-06-15 | 北京大学口腔医学院 | A kind of digitlization row's tooth method based on root information |
-
2016
- 2016-11-30 US US16/465,565 patent/US20200015936A1/en not_active Abandoned
- 2016-11-30 JP JP2019528839A patent/JP2019536561A/en not_active Ceased
- 2016-11-30 CN CN201680091236.8A patent/CN110087577B/en active Active
- 2016-11-30 KR KR1020197018733A patent/KR20190087593A/en unknown
- 2016-11-30 EP EP16813182.9A patent/EP3547949B1/en active Active
- 2016-11-30 PL PL16813182.9T patent/PL3547949T3/en unknown
- 2016-11-30 WO PCT/US2016/064102 patent/WO2018101923A1/en unknown
-
2021
- 2021-12-20 US US17/555,797 patent/US11896455B2/en active Active
Patent Citations (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030039389A1 (en) | 1997-06-20 | 2003-02-27 | Align Technology, Inc. | Manipulating a digital dentition model to form models of individual dentition components |
US20080248443A1 (en) * | 1997-06-20 | 2008-10-09 | Align Technology, Inc | Clinician review of an orthodontic treatment plan and appliance |
US20060134581A1 (en) | 2003-07-23 | 2006-06-22 | Orametrix, Inc. | Automatic crown and gingiva detection from three-dimensional virtual model of teeth |
US20060093992A1 (en) | 2004-11-02 | 2006-05-04 | Huafeng Wen | Method and apparatus for manufacturing and constructing a physical dental arch model |
US20060134580A1 (en) | 2004-12-17 | 2006-06-22 | 3M Innovative Properties Company | RFID tracking of patient-specific orthodontic materials |
US20070188601A1 (en) | 2006-02-13 | 2007-08-16 | Janos Rohaly | Three-channel camera systems with non-collinear apertures |
US20110004331A1 (en) | 2007-12-21 | 2011-01-06 | 3M Innovative Properties Company | Methods of preparing a virtual dentition model and fabricating a dental retainer therefrom |
US8738165B2 (en) * | 2007-12-21 | 2014-05-27 | 3M Innovative Properties Company | Methods of preparing a virtual dentition model and fabricating a dental retainer therefrom |
US20140067334A1 (en) * | 2012-09-06 | 2014-03-06 | Align Technology Inc. | Method and a system usable in creating a subsequent dental appliance |
US20160199154A1 (en) | 2013-08-14 | 2016-07-14 | 3M Innovative Properties Company | An orthodontic bracket and a method of making an orthodontic bracket |
US20170105814A1 (en) | 2014-05-22 | 2017-04-20 | Industry-Academic-Cooperation Foundation Chosun University | Method of fabricating custom dental correction device, and custom dental correction device fabricated by same |
US20160004811A1 (en) * | 2014-07-01 | 2016-01-07 | 3M Innovative Properties Company | Detecting tooth wear using intra-oral 3d scans |
US20190159868A1 (en) | 2016-07-28 | 2019-05-30 | Carestream Dental Technology Topco Limited | Method and System for Dentition Mesh Braces Removal |
US11058514B2 (en) * | 2016-07-28 | 2021-07-13 | Carestream Dental Technology Topco Limited | Method and system for dentition mesh braces removal |
US20200015936A1 (en) | 2016-11-30 | 2020-01-16 | Carestream Dental Technology Topco Limited | Method and system for braces removal from dentition mesh |
Non-Patent Citations (7)
Title |
---|
D. L. Page et al., "Perception-based 3D Triangle Mesh Segmentation Using Fast Marching Watersheds," Proc. Int. Conf. on Computer Vision and Pattern Recognition, II:27-32, (Jun. 2003). |
International Preliminary Report on Patentability received for PCT Patent Application No. PCT/US2016/064102, dated Jun. 13, 2019, 9 pages. |
International Search Report and Written Opinion received for PCT Patent Application No. PCT/US2016/064102, dated Jul. 28, 2017, 10 pages. |
Joe Min Moon, "Evaluation of Software Developed for Automated Segmentation of Digital Dental Models," Thesis, 58 pages, (Feb. 2012). |
Thomas Kronfeld et al., "Snake-Based Segmentation of Teeth from Virtual Dental Casts," Computer-Aided Design and Applications, 7(a), 12 pages (2010). |
U.S. Appl. No. 16/465,565, filed May 30, 2019, 2020/0015936, Abandoned. |
Wei Zhao et al., "A robust hole-filling algorithm for triangular mesh," The Visual Computer, 23(12):987-997, (Dec. 2007). |
Also Published As
Publication number | Publication date |
---|---|
WO2018101923A1 (en) | 2018-06-07 |
EP3547949B1 (en) | 2023-11-29 |
EP3547949C0 (en) | 2023-11-29 |
PL3547949T3 (en) | 2024-03-04 |
EP3547949A1 (en) | 2019-10-09 |
CN110087577B (en) | 2022-11-08 |
US20220233275A1 (en) | 2022-07-28 |
KR20190087593A (en) | 2019-07-24 |
US20200015936A1 (en) | 2020-01-16 |
CN110087577A (en) | 2019-08-02 |
JP2019536561A (en) | 2019-12-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11896455B2 (en) | Method and system for braces removal from dentition mesh | |
US11058514B2 (en) | Method and system for dentition mesh braces removal | |
JP7289026B2 (en) | Method and Apparatus for Hybrid Mesh Segmentation | |
US10339649B2 (en) | Method and system for hybrid mesh segmentation | |
CN110313037B (en) | Longitudinal analysis and visualization in a limited precision system | |
US9191648B2 (en) | Hybrid stitching | |
US8135569B2 (en) | System and method for three-dimensional complete tooth modeling | |
CN114730466A (en) | Automatic detection, generation and/or correction of tooth features in digital models | |
EP3349680B1 (en) | Method for creating flexible arch model of teeth for use in restorative dentistry | |
EP3673864A1 (en) | Tooth segmentation using tooth registration | |
US20220012888A1 (en) | Methods and system for autonomous volumetric dental image segmentation | |
US20220101618A1 (en) | Dental model superimposition using clinical indications | |
US11961238B2 (en) | Tooth segmentation using tooth registration |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
AS | Assignment |
Owner name: CARESTREAM HEALTH, INC., NEW YORK Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:YE, WEI;CHEN, SHOUPU;REYNARD, DELPHINE;AND OTHERS;SIGNING DATES FROM 20161201 TO 20161205;REEL/FRAME:063369/0804 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
AS | Assignment |
Owner name: CARESTREAM DENTAL LLC, GEORGIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CARESTREAM DENTAL TECHNOLOGY TOPCO LIMITED;REEL/FRAME:064277/0887 Effective date: 20200731 Owner name: CARESTREAM DENTAL TECHNOLOGY TOPCO LIMITED, UNITED KINGDOM Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CARESTREAM HEALTH, INC.;REEL/FRAME:064278/0079 Effective date: 20171026 |
|
AS | Assignment |
Owner name: DENTAL IMAGING TECHNOLOGIES CORPORATION, PENNSYLVANIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CARESTREAM DENTAL LLC;REEL/FRAME:064492/0348 Effective date: 20220420 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: AWAITING TC RESP., ISSUE FEE NOT PAID |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: AWAITING TC RESP., ISSUE FEE NOT PAID |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT RECEIVED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
AS | Assignment |
Owner name: CARESTREAM HEALTH, INC., NEW YORK Free format text: NUNC PRO TUNC ASSIGNMENT;ASSIGNOR:TROPHY SAS;REEL/FRAME:066470/0603 Effective date: 20161129 |